105
Semantic disambiguation
nWord sense
nChoosing most correct sense for a word in context
nProblem: WordNet senses too narrow (large # of senses)
nAvg. 4.74 for nouns (not a big problem)
nAvg. 8.63; high of 41 senses for verbs (a problem)
nSemantic classes
nSelect appropriate WordNet semantic class of word in context
nAn easier, more plausible task
n
Problem:  Lexical entries in WordNet can dozens of different senses.

In order to make a semantic representation, we need to decide which meaning is most appropriate.  This task is called Word Sense Diambiguation – but WordNet’s senses are too-fined grained to make this a plausible task for untrained native speakers, and too difficult of a task to model in one step.  So we are working on an intermediate goal: Semantic Class Disambiguation.